PropertyComparisonProcessor: use deduplicated values for determining …

…deviations and omissions to avoid duplicated reporting
fusion-jena · Dec 19, 2024 · c8e5155 · c8e5155
1 parent 0addb4c
commit c8e5155
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 6 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,7 +6,10 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ## [Unreleased]
 
 ### Fixed
-* fix `PopulationComparisonProcessor`: fix measurement of **Absolute Coveredness** to not increase in case of a duplicated resource in one dataset without a corresponding resource in any other dataset  
+* fix `PopulationComparisonProcessor`: fix measurement of **Absolute Coveredness** to not increase in case of a duplicated resource in one dataset without a corresponding resource in any other dataset
+
+### Changed
+* changed `PropertyComparisonProcessor`: use deduplicated values for determining deviations and omissions to avoid duplicated reporting
 
 ## [3.1.1] - 2024-11-13
 

diff --git a/...ore/src/main/java/de/uni_jena/cs/fusion/abecto/processor/PropertyComparisonProcessor.java b/...ore/src/main/java/de/uni_jena/cs/fusion/abecto/processor/PropertyComparisonProcessor.java
@@ -380,16 +380,16 @@ protected void reportDeviationsAndOmissions() {
 
     protected void reportDeviationsAndOmissionsForDatasetPair(ResourcePair datasetPair) {
         for (String variable : variables) {
-            Map<Resource, Map<RDFNode, Set<Resource>>> resourcesByNonDistinctValueByDataset = resourcesByNonDistinctValueByDatasetByVariable.get(variable);
+            Map<Resource, Map<RDFNode, Set<Resource>>> resourcesByDistinctValueByDataset = resourcesByDistinctValueByDatasetByVariable.get(variable);
             if (theAspect.variableCoveredByDatasets(variable, datasetPair.first, datasetPair.second)) {
-                Map<RDFNode, Set<Resource>> resourceByNonDistinctValuesOfFirstDataset = resourcesByNonDistinctValueByDataset.get(datasetPair.first);
-                Map<RDFNode, Set<Resource>> resourceByNonDistinctValuesOfSecondDataset = resourcesByNonDistinctValueByDataset.get(datasetPair.second);
+                Map<RDFNode, Set<Resource>> resourceByDistinctValuesOfFirstDataset = resourcesByDistinctValueByDataset.get(datasetPair.first);
+                Map<RDFNode, Set<Resource>> resourceByDistinctValuesOfSecondDataset = resourcesByDistinctValueByDataset.get(datasetPair.second);
                 for (Resource firstResource : correspondingResourcesByDataset.get(datasetPair.first)) {
                     for (Resource secondResource : correspondingResourcesByDataset.get(datasetPair.second)) {
                         Set<RDFNode> uncoveredValuesOfFirstResource =
-                                getUncoveredValuesOfResource(firstResource, secondResource, resourceByNonDistinctValuesOfFirstDataset, resourceByNonDistinctValuesOfSecondDataset);
+                                getUncoveredValuesOfResource(firstResource, secondResource, resourceByDistinctValuesOfFirstDataset, resourceByDistinctValuesOfSecondDataset);
                         Set<RDFNode> uncoveredValuesOfSecondResource =
-                                getUncoveredValuesOfResource(secondResource, firstResource, resourceByNonDistinctValuesOfSecondDataset, resourceByNonDistinctValuesOfFirstDataset);
+                                getUncoveredValuesOfResource(secondResource, firstResource, resourceByDistinctValuesOfSecondDataset, resourceByDistinctValuesOfFirstDataset);
 
                         // deviation: a pair of resources with each having a value not present in the
                         // other resource